CN111724598A - Method, device, equipment and storage medium for planning path - Google Patents
Method, device, equipment and storage medium for planning path Download PDFInfo
- Publication number
- CN111724598A CN111724598A CN202010602917.4A CN202010602917A CN111724598A CN 111724598 A CN111724598 A CN 111724598A CN 202010602917 A CN202010602917 A CN 202010602917A CN 111724598 A CN111724598 A CN 111724598A
- Authority
- CN
- China
- Prior art keywords
- value
- obstacle
- target
- data frame
- evaluation value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096805—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route
Abstract
The application discloses a method, a device, equipment and a storage medium for planning a path, and relates to the field of automatic driving. The specific implementation scheme is as follows: acquiring a target obstacle data frame; determining a target evaluation value corresponding to the target obstacle data frame according to a pre-trained obstacle avoidance model and the target obstacle data frame, wherein the obstacle avoidance model is used for representing the corresponding relation between the obstacle data frame and the evaluation value; acquiring a historical evaluation value corresponding to a historical obstacle data frame; determining an obstacle avoidance value of the target obstacle according to the target evaluation value and the historical evaluation value; and in response to determining that the obstacle avoidance value is greater than the preset threshold value, planning a path around the target obstacle indicated by the target obstacle data frame. According to the implementation mode, the obstacle avoidance value of the target obstacle is determined by combining the historical evaluation value, so that the vehicle can accurately judge whether to avoid the obstacle according to the determined obstacle avoidance value, and the driving intelligence and safety of the vehicle are improved.
Description
Technical Field
The present application relates to the field of data processing, in particular to the field of automatic driving, and more particularly, to a method, an apparatus, a device, and a storage medium for planning a path.
Background
When the unmanned vehicle avoids the obstacles, a general method is to calculate a curve bypassing all the obstacles by a mathematical optimization method. However, at some time, such as a red light in a queue before the intersection, or when the vehicle in front is faster than the vehicle in the front, the unmanned vehicle should not bypass the obstacle in front but wait behind it. For obstacles that need to be and do not need to be bypassed, the processing mode of the path planning algorithm is often inaccurate.
Disclosure of Invention
The present disclosure provides a method, apparatus, device, and storage medium for planning a path.
According to an aspect of the present disclosure, there is provided a method for planning a path, including: acquiring a target obstacle data frame; determining a target evaluation value corresponding to the target obstacle data frame according to a pre-trained obstacle avoidance model and the target obstacle data frame, wherein the obstacle avoidance model is used for representing the corresponding relation between the obstacle data frame and the evaluation value; acquiring a historical evaluation value corresponding to a historical obstacle data frame; determining an obstacle avoidance value of the target obstacle according to the target evaluation value and the historical evaluation value; and in response to determining that the obstacle avoidance value is greater than the preset threshold value, planning a path around the target obstacle indicated by the target obstacle data frame.
According to another aspect of the present disclosure, there is provided an apparatus for planning a path, comprising: a data frame acquisition unit configured to acquire a target obstacle data frame; the evaluation value determining unit is configured to determine a target evaluation value corresponding to a target obstacle data frame according to a pre-trained obstacle avoidance model and the target obstacle data frame, wherein the obstacle avoidance model is used for representing the corresponding relation between the obstacle data frame and the evaluation value; a history evaluation value acquisition unit configured to acquire a history evaluation value corresponding to the history obstacle data frame; an obstacle avoidance value determination unit configured to determine an obstacle avoidance value of the target obstacle according to the target evaluation value and the historical evaluation value; a path planning unit configured to plan a path that bypasses the target obstacle indicated by the target obstacle data frame in response to determining that the obstacle avoidance value is greater than the preset threshold value.
According to yet another aspect of the present disclosure, there is provided an electronic device for planning a path, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method for planning a path as described above.
According to yet another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method for planning a path as described above.
According to the technology of the application, the problem that the processing mode of a path planning algorithm is often inaccurate for the obstacles which need to be bypassed or do not need to be bypassed is solved, and the obstacle avoidance value of the target obstacle is determined by combining the historical evaluation value, so that the vehicle can accurately judge whether to bypass the obstacle or not according to the determined obstacle avoidance value, and the driving intelligence and safety of the vehicle are improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for planning a path according to the present application;
FIG. 3 is a schematic diagram of an application scenario of a method for planning a path according to the present application;
FIG. 4 is a flow diagram of another embodiment of a method for planning a path according to the present application;
FIG. 5 is a schematic diagram of an embodiment of an apparatus for planning a path according to the present application;
fig. 6 is a block diagram of an electronic device for implementing the method for planning a path according to an embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows an exemplary system architecture 100 to which embodiments of the present method for planning a path or apparatus for planning a path may be applied.
As shown in fig. 1, the system architecture 100 may include a cart 101, a camera 102 disposed on the cart 101, a lidar 103 disposed on the cart 101, a network 104, and a server 105. Network 104 is used to provide a medium for communication links between camera 102, lidar 103, and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The camera 102, lidar 103 may interact with a server 105 through a network 104 to receive or transmit messages. The camera 102 and the laser radar 103 may collect a target obstacle data frame in the vehicle driving direction in real time, and send the collected obstacle data frame information to the server 105 through the network 104, or store the information locally. The camera 102 and the laser radar 103 may be fixed to the vehicle to capture images of all data frames including obstacle information in front of the vehicle.
The server 105 may acquire the acquired data frame including the obstacle from the camera 102 and the laser radar 103, and process and calculate the target obstacle data frame.
It should be noted that the method for planning a path provided in the embodiment of the present application may be executed by the server 105. Accordingly, means for planning a path may be provided in the server 105.
It should be understood that the number of cameras, networks, and servers in fig. 1 is merely illustrative. There may be any number of cameras, lidar, networks, and servers, as desired for implementation.
With continued reference to fig. 2, a flow 200 of one embodiment of a method for planning a path in accordance with the present application is shown. The method for planning the path of the embodiment comprises the following steps:
In this embodiment, an executing subject (for example, the terminal device 104 shown in fig. 1) of the method for planning a path may acquire a target obstacle data frame in real time from an image captured by a camera or a radar (for example, the camera 102 and the laser radar 103 shown in fig. 1) through a wired connection or a wireless connection. For example, the same obstacle is acquired 60 times a second by a camera or lidar, and each acquired data may be taken as an obstacle data frame. The obstacle data frame includes information of an obstacle. The target obstacle data frame may include a data frame of an obstacle ahead of the current time of vehicle travel or a data frame of an obstacle at the current time in any direction of interest. It is to be understood that the target obstacle data frame may include current frame data of the target obstacle extracted by target detection or semantic segmentation from a current frame image of the target obstacle.
After the execution main body obtains the target obstacle data frame in real time, the target evaluation value corresponding to the target obstacle data frame can be determined according to the pre-trained obstacle avoidance model and the target obstacle data frame. The pre-trained obstacle avoidance model may be, for example, a generalized linear regression model, and the generalized linear regression model is used to represent a correspondence between the obstacle data frame and the evaluation value. For example, after the target obstacle data frame is input to the generalized linear regression model, the target evaluation value corresponding to the target obstacle data frame may be determined directly from the correspondence relationship of the model training. The evaluation value is used to evaluate whether the obstacle needs to be bypassed, and the target evaluation value may be a score corresponding to the target obstacle data frame. The target evaluation value may be used to characterize how urgently the need to avoid an obstacle in the target obstacle data frame is, with a larger target evaluation value indicating a more urgent need. Preferably, the value range of the target evaluation value may be any number between 0 and 1, and the value range of the target evaluation value is not specifically limited in the present application. It is understood that, after determining the target evaluation value corresponding to the target obstacle data frame by using the obstacle avoidance model, the executing subject may store the target evaluation value for use in subsequent processing.
The execution subject may acquire a history evaluation value corresponding to the history obstacle data frame. Specifically, the historical obstacle data frame refers to an obstacle data frame that is one frame before the target obstacle data frame. The historical evaluation value corresponding to the historical obstacle data frame is calculated by the evaluation value of the previous data frame of the historical obstacle data frame. By analogy, it can be known that, if the target obstacle data frame is the nth data frame, the historical obstacle data frame is the nth-1 data frame, and the historical evaluation value obtained in step 203 is the nth-1 data frame. The historical evaluation value of the (n-1) th data frame is obtained through the evaluation value of the (n-2) th data frame, and the like, the historical evaluation value of the (n-1) th data frame is generally calculated by the execution subject according to the evaluation values of the (1) th data frame to the (n-2) th data frame and is stored in a database, a server or the local of the execution subject. When the historical evaluation value corresponding to the historical obstacle data frame needs to be used, the execution subject may acquire the historical evaluation value corresponding to the historical obstacle data frame from a database or a server, or may locally acquire the historical evaluation value from the execution subject. The source of the historical evaluation value is not particularly limited in the present application. The above-mentioned historical evaluation value can be obtained from the pre-trained obstacle avoidance model mentioned in step 202. The historical evaluation value may be specifically used to characterize whether an obstacle indicated by the corresponding historical obstacle data frame needs to be avoided. The historical evaluation value may be an obstacle avoidance score corresponding to the historical obstacle data frame.
And step 204, determining an obstacle avoidance value of the target obstacle according to the target evaluation value and the historical evaluation value.
After obtaining the target evaluation value corresponding to the target obstacle data frame and the historical evaluation value corresponding to the historical obstacle data frame, the execution main body may determine an obstacle avoidance value of the target obstacle according to the target evaluation value and the historical evaluation value. Specifically, the execution subject may multiply the target evaluation value by its corresponding weight to obtain a target output value. And multiplying the historical evaluation value of the previous data frame of the obstacle by the corresponding weight to obtain a historical output value. And adding or averaging the target output value and the historical output value to obtain a final output value, namely the obstacle avoidance value of the target obstacle. The obstacle avoidance value can be used to characterize whether an obstacle needs to be avoided.
And step 205, in response to determining that the obstacle avoidance value is greater than the preset threshold value, planning a path which bypasses the target obstacle indicated by the target obstacle data frame.
After obtaining the obstacle avoidance value of the target obstacle, the execution subject may compare the obstacle avoidance value with a preset threshold. In response to determining that the obstacle avoidance value is greater than the preset threshold, a path may be planned that bypasses the target obstacle indicated by the target obstacle data frame. Correspondingly, if the obstacle avoidance value is smaller than or equal to the preset threshold value, the target obstacle can be followed. Specifically, the range of the obstacle avoidance value may be set to any number of 0 to 1, and the preset threshold may be set to a neutral value of 0.5. The preset threshold value set to 0.5 may mean that when the obstacle avoidance value exceeds 0.5, it indicates that the obstacle corresponding to the obstacle avoidance value needs to be avoided, and when the obstacle avoidance value does not exceed 0.5, it indicates that the obstacle corresponding to the obstacle avoidance value does not need to be avoided. Of course, the preset threshold value can also be set to any number of 0-1, or reasonably set according to the numerical value of the obstacle avoidance value, and the range of the obstacle avoidance value and the preset threshold value are not specifically limited in the application.
And when determining that the obstacle avoidance value corresponding to the target obstacle indicated by the target obstacle data frame is greater than the preset threshold value, the execution main body indicates that the obstacle needs to be bypassed.
With continued reference to fig. 3, a schematic diagram of one application scenario of the method for planning a path according to the present application is shown. In the application scenario of fig. 3, the onboard camera 302 on the vehicle 301 collects data frames of the target obstacle 305 in real time, including, for example, the 1 st frame, the 2 nd frame, the 3 rd frame, and the 4 th frame in fig. 3. The data frames of the obstacles acquired in real time include a target obstacle data frame acquired in real time, such as 303 th frame in fig. 3, and acquired historical obstacle data frames, such as 1 st frame, 2 nd frame and 3 rd frame in fig. 3. A vehicle-mounted computer (not shown in fig. 3) in the vehicle 301 acquires a target obstacle data frame, for example, frame 4 of fig. 3 at 303 in real time, and determines a target evaluation value 0.4 corresponding to the target obstacle data frame according to a pre-trained obstacle avoidance model and the target obstacle data frame. An on-board computer (not shown in fig. 3) in the vehicle 301 acquires an evaluation value corresponding to the historical obstacle data frame, for example, 0.8 corresponding to the 3 rd frame in fig. 3. An on-board computer (not shown in fig. 3) in the vehicle 301 determines an obstacle avoidance value 0.7 corresponding to the target obstacle according to a target evaluation value 0.4 (e.g., an evaluation value corresponding to frame 4 in fig. 3) and a historical evaluation value 0.8 (e.g., an evaluation value corresponding to frame 3 in fig. 3); and when the vehicle-mounted computer determines that the obstacle avoidance value 0.7 is greater than the preset threshold value 0.5, planning a path 304 which bypasses the target obstacle indicated by the target obstacle data.
According to the method and the device, the obstacle avoidance value of the target obstacle is determined by combining the historical evaluation value, so that the vehicle can accurately judge whether to avoid the obstacle according to the determined obstacle avoidance value, and the driving intelligence and safety of the vehicle are improved.
With continued reference to fig. 4, a flow 400 of another embodiment of a method for planning a path of the present application is shown. As shown in fig. 4, the method for planning a path of the present embodiment may include the following steps:
The principle of steps 401 to 403 is similar to that of steps 201 to 203, and is not described herein again.
After obtaining the historical evaluation value, the execution subject may determine a historical decision value according to the historical evaluation value and a preset threshold. The decision value is used to characterize avoiding an obstacle or not avoiding an obstacle. May be set to perform a binary number 0 or 1 that the body can recognize. For example, when the decision value is set to 1, the execution subject controls the vehicle to avoid the obstacle; and when the decision value is set to be 0, the execution main body controls the vehicle not to avoid the obstacle. When the historical evaluation value is larger than a preset threshold value, determining the historical decision value to be 1; when the historical evaluation value is less than or equal to a preset threshold value, the historical decision value is determined to be 0.
The historical evaluation value can be an evaluation value which is corresponding to the historical obstacle data frame and used for representing whether to bypass the obstacle, and can be a fractional value, and the range can be 0-1. For example, the value range of the historical evaluation value is set to any value between 0 and 1, and the preset threshold value may be set to a neutral value between 0 and 1, for example, 0.5. When the preset threshold value is set to be 0.5, and the historical evaluation value exceeds 0.5, the obstacle corresponding to the historical evaluation value needs to be bypassed, and the corresponding historical decision value is 1; when the historical evaluation value is not more than 0.5, the obstacle corresponding to the historical evaluation value does not need to be bypassed, and the corresponding historical decision value is 0.
After obtaining the historical decision value, the executive body may determine an obstacle avoidance value of the target obstacle according to the target evaluation value, the historical decision value, a first preset weight corresponding to the target evaluation value, a second preset weight corresponding to the historical evaluation value, and a third preset weight corresponding to the historical decision value. Specifically, the obstacle avoidance value of the target obstacle may be determined by a target evaluation value × first preset weight, a history evaluation value × second preset weight, and a history decision value × third preset weight. Specifically, the obstacle avoidance value of the target obstacle may be determined by adding or averaging the target evaluation value and the first preset weight, the historical evaluation value and the second preset weight, and the historical decision value and the third preset weight. The first preset weight, the second preset weight and the third preset weight are hyper-parameters, the hyper-parameters are parameters set before the pre-trained obstacle avoidance model starts a learning process, and the hyper-parameters are not parameter data obtained through training. The execution main body can optimize the hyper-parameters so as to improve the performance and effect of the pre-trained obstacle avoidance model, and can adjust and optimize the hyper-parameters according to the model training result. The method has the advantages that the historical decision value is added to determine the obstacle avoidance value of the target obstacle, so that decision jumping of the current data frame cannot occur when the confidence coefficient of the evaluation value of the current data frame is not high enough, and the decision value of the current data frame cannot jump accordingly even if the evaluation value output by the current data frame is slightly deviated, so that repeated jumping of the decision value can be prevented, user experience is improved, and vehicle driving safety is improved.
Specifically, when an obstacle avoidance value of an obstacle indicated by the third data frame needs to be determined, an evaluation value of the second data frame and a decision value for the second data frame need to be obtained, the evaluation value of the second data frame is obtained through a pre-trained obstacle avoidance model, and the setting range can be set to be 0-1. For example, the obstacle is traveling ahead at a faster speed than the vehicle because the obstacle is ahead and faster than the vehicle speed, and the obstacle does not need to be avoided, at this time, the evaluation value of the first data frame of the obstacle by the executing subject, for example, 0 or a numerical value such as 0.01, 0.05, etc., which is smaller than the preset threshold value 0.5, and the decision value of the executing subject for the first data frame of the obstacle is also 0 because the evaluation value of the first data frame is smaller than the preset threshold value, indicating that the obstacle does not need to be avoided. When the executing main body analyzes the second data frame of the obstacle, for example, a value greater than a preset threshold 0.5, such as an evaluation value of 1 or 0.8, of the second data frame of the obstacle is obtained, an obstacle avoidance value of the target obstacle indicated by the second data frame may be calculated in the following manner:
the obstacle avoidance value of the target obstacle indicated by the second data frame is the evaluation value of the second data frame and the first preset weight, the evaluation value of the first data frame and the second preset weight, and the decision value of the first data frame and the third preset weight. For example, if the obstacle avoidance value of the target obstacle indicated by the second data frame is 1 × 0.6+ 0.3+0 × 0.1 ═ 0.6> the preset threshold value 0.5, the decision value of the second data frame is 1, indicating that the executing subject needs to control the vehicle to avoid the obstacle. The method for calculating the obstacle avoidance value of the target obstacle is not particularly limited.
In the embodiment, when the obstacle avoidance value of the target obstacle is determined, the historical decision value is added for calculation, so that when the confidence coefficient of the evaluation value of the current data frame is not high enough, decision jumping does not occur in the decision of the current data frame, and even if the evaluation value output by the current data frame is slightly deviated, the decision value of the current data frame does not jump accordingly, so that repeated jumping of the decision value can be prevented, the user experience is improved, and the safety of vehicle driving is improved.
When the execution subject determines that the target obstacle data frame is the first data frame, and there is no history data frame at this time, the history evaluation value corresponding to the history data frame and the history decision value corresponding to the history data frame may be determined as a first preset value and a second preset value, respectively. For example, they may each be set to a neutral value between 0 and 1, and may be 0.5, 0.5. That is, the historical evaluation value is set to 0.5, and the historical decision value is set to 0.5. The execution body does not determine whether the set numerical value avoids the obstacle. And then, determining a target evaluation value of the first data frame of the obstacle according to a pre-trained obstacle avoidance model.
After obtaining the target evaluation value, the execution subject may determine an obstacle avoidance value of the target obstacle according to the first preset value, the second preset value, the target evaluation value, the first preset weight, the second preset weight, and the third preset weight. Namely, the obstacle avoidance value of the target obstacle is equal to the target evaluation value, namely, the first preset weight + the first preset value, namely, the second preset weight + the second preset weight, namely, the third preset weight. For example, the obstacle avoidance value of the target obstacle is the target evaluation value +0.5 × the second preset weight +0.5 × the third preset weight.
In this embodiment, when the target obstacle data frame is the first data frame, the evaluation value and the decision value of the historical data frame are set as preset values, so that the accuracy of calculating the obstacle avoidance value of the target obstacle is improved.
The principle of step 407 is similar to that of step 205, and is not described herein again.
In some optional implementations of this embodiment, a sum of the first preset weight, the second preset weight, and the third preset weight is a third preset value.
In this implementation, a sum of the first preset weight, the second preset weight, and the third preset weight is a third preset value, and the third preset value is a constant, and may be, for example, 1, or 2, 5, or 8. The first preset weight, the second preset weight and the third preset weight are preset hyper-parameters which can enable the pre-trained obstacle avoidance model to have the optimal performance and the best effect.
According to the implementation mode, the sum of the first preset weight, the second preset weight and the third preset weight is set as the third preset value, so that the first preset weight, the second preset weight and the third preset weight can be optimized, one of the weights can be modified, and the other two weights can be changed along with the modified first preset weight, so that the parameter optimization of the pre-trained obstacle avoidance model can be realized, and the accuracy of the result output of the pre-trained obstacle avoidance model is improved.
In some optional implementations of this embodiment, the third preset weight is smaller than the first preset weight.
In this implementation manner, the third preset weight must be smaller than the first preset weight, so that flexible decision switching can be realized. Otherwise decision switching never occurs for the same obstacle. The larger the second preset weight is, the less the decision is likely to be changed, so the second preset weight is not set to exceed 0.5.
For example, when the third preset weight is greater than the first preset weight, the third preset weight is set to 0.5, the second preset weight is set to 0.2, and the first preset weight is set to 0.3, the evaluation value of the first data frame is 0.2 and the decision value of the corresponding first data frame is 0 for the same obstacle, which indicates that the obstacle is not avoided, and when the evaluation value of the second data frame is 1, the obstacle avoidance value of the second data frame is 1 × 0.3+0.2 +0.5 — 0.34< the preset threshold value 0.5, so that the decision value of the second data frame is 0 for the same obstacle, which is also not avoided.
For example, when the third preset weight is greater than the first preset weight, the third preset weight is set to 0.5, the second preset weight is set to 0.1, and the first preset weight is set to 0.4, for the same obstacle, the evaluation value of the first data frame is 0.2, and the decision value of the corresponding first data frame is 0, which indicates that the obstacle is not avoided, and when the evaluation value of the second data frame is 1, the obstacle avoidance value of the second data frame is 1 × 0.4+0.2 + 0.1+0 × 0.5 is 0.42< the preset threshold value 0.5, so that, for the same obstacle, the decision value of the second data frame is 0, which is also not avoided, and therefore, when the third preset weight is greater than the first preset weight, the decision value is not changed. The decision value can be flexibly changed only if the third preset weight is smaller than the first preset weight.
For example, when the third preset weight is smaller than the first preset weight, the third preset weight is set to 0.4, the second preset weight is set to 0.1, and the first preset weight is set to 0.5, the evaluation value of the first data frame is 0.2 and the decision value of the corresponding first data frame is 0 for the same obstacle, which indicates that the obstacle is not avoided, and when the evaluation value of the second data frame is 1, the obstacle avoidance value of the second data frame is 1 × 0.5+0.2 × 0.1+ 0.4 — 0.52> and the preset threshold value is 0.5, so that the decision value of the second data frame is 1 for the same obstacle, which avoids the obstacle.
For example, when the third preset weight is smaller than the first preset weight, the third preset weight is set to 0.3, the second preset weight is set to 0.3, and the first preset weight is set to 0.4, the evaluation value of the first data frame is 0.2 and the decision value of the corresponding first data frame is 0 for the same obstacle, which indicates that the obstacle is not avoided, and when the evaluation value of the second data frame is 1, the obstacle avoidance value of the second data frame is 1 × 0.4+0.2 × 0.13+ 0.3 ═ 0.426< preset threshold 0.5, so that the decision value of the second data frame is 0 and the obstacle is not avoided for the same obstacle.
With further reference to fig. 5, as an implementation of the method shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for planning a path, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 5, the apparatus 500 for planning a path of the present embodiment includes: a data frame acquisition unit 501, an evaluation value determination unit 502, a history evaluation value acquisition unit 503, an obstacle avoidance value determination unit 504, and a path planning unit 505.
A data frame acquisition unit 501 configured to acquire a target obstacle data frame.
An evaluation value determining unit 502 configured to determine a target evaluation value corresponding to the target obstacle data frame according to a pre-trained obstacle avoidance model and the target obstacle data frame, wherein the obstacle avoidance model is used for representing a corresponding relationship between the obstacle data frame and the evaluation value.
A history evaluation value acquisition unit 503 configured to acquire a history evaluation value corresponding to the history obstacle data frame.
An obstacle avoidance value determination unit 504 configured to determine an obstacle avoidance value of the target obstacle from the target evaluation value and the historical evaluation value.
A path planning unit 505 configured to plan a path that bypasses the target obstacle indicated by the target obstacle data frame in response to determining that the obstacle avoidance value is greater than the preset threshold value.
In some optional implementations of the present embodiment, the obstacle avoidance value determining unit 504 is further configured to: determining a historical decision value according to the historical evaluation value and a preset threshold value; and determining an obstacle avoidance value of the target obstacle according to the target evaluation value, the historical decision value, a first preset weight corresponding to the target evaluation value, a second preset weight corresponding to the historical evaluation value and a third preset weight corresponding to the historical decision value.
In some optional implementations of the present embodiment, the obstacle avoidance value determining unit 504 is further configured to: and in response to the fact that the target obstacle data frame is determined to be the first data frame, determining the historical evaluation value and the historical decision value to be a first preset value and a second preset value respectively, and determining the obstacle avoidance value of the target obstacle according to the first preset value, the second preset value, the target evaluation value, the first preset weight, the second preset weight and the third preset weight.
In some optional implementations of this embodiment, a sum of the first preset weight, the second preset weight, and the third preset weight is a third preset value.
In some optional implementations of this embodiment, the third preset weight is smaller than the first preset weight.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
Fig. 6 is a block diagram of an electronic device for planning a path according to an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 6, the electronic apparatus includes: one or more processors 601, memory 602, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses 605 and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses 605 may be used, along with multiple memories and multiple memories, if desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 6, one processor 601 is taken as an example.
The memory 602 is a non-transitory computer readable storage medium as provided herein. The memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method for planning a path provided herein. A non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the method for planning a path provided herein.
The memory 602, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and units, such as program instructions/units corresponding to the method for planning a path in the embodiment of the present application (for example, the data frame acquisition unit 501, the evaluation value determination unit 502, the historical evaluation value acquisition unit 503, the obstacle avoidance value determination unit 504, and the path planning unit 505 shown in fig. 5). The processor 601 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 602, that is, implements the method for planning a path in the above method embodiment.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device for the method of planning a path, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 optionally includes memory located remotely from the processor 601, and these remote memories may be connected over a network to the electronic device used in the method of planning a path. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the method for planning a path may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603, and the output device 604 may be connected by a bus 605 or other means, and are exemplified by the bus 605 in fig. 6.
The input device 603 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus for the method of planning a path, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or other input devices. The output devices 604 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme of the embodiment of the application, the obstacle avoidance value of the target obstacle is determined by combining the historical evaluation value, so that the vehicle can accurately judge whether to avoid the obstacle according to the determined obstacle avoidance value, and the driving intelligence and safety of the vehicle are improved.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (12)
1. A method for planning a path, comprising:
acquiring a target obstacle data frame;
determining a target evaluation value corresponding to the target obstacle data frame according to a pre-trained obstacle avoidance model and the target obstacle data frame, wherein the obstacle avoidance model is used for representing the corresponding relation between the obstacle data frame and the evaluation value;
acquiring a historical evaluation value corresponding to a historical obstacle data frame;
determining an obstacle avoidance value of the target obstacle according to the target evaluation value and the historical evaluation value;
in response to determining that the obstacle avoidance value is greater than a preset threshold, planning a path that bypasses a target obstacle indicated by the target obstacle data frame.
2. The method of claim 1, wherein the determining an obstacle avoidance value for the target obstacle from the target evaluation value and the historical evaluation value comprises:
determining a historical decision value according to the historical evaluation value and a preset threshold value;
and determining an obstacle avoidance value of the target obstacle according to the target evaluation value, the historical decision value, a first preset weight corresponding to the target evaluation value, a second preset weight corresponding to the historical evaluation value and a third preset weight corresponding to the historical decision value.
3. The method of claim 2, wherein the determining an obstacle avoidance value for the target obstacle from the target evaluation value and the historical evaluation value comprises:
in response to determining that the target obstacle data frame is a first data frame, determining the historical evaluation value and the historical decision value as a first preset value and a second preset value respectively;
and determining an obstacle avoidance value of the target obstacle according to the first preset value, the second preset value, the target evaluation value, the first preset weight, the second preset weight and the third preset weight.
4. The method of claim 3, wherein a sum of the first, second, and third preset weights is a third preset value.
5. The method of claim 4, wherein the third preset weight is less than the first preset weight.
6. An apparatus for planning a path, comprising:
a data frame acquisition unit configured to acquire a target obstacle data frame;
an evaluation value determining unit, configured to determine a target evaluation value corresponding to the target obstacle data frame according to a pre-trained obstacle avoidance model and the target obstacle data frame, wherein the obstacle avoidance model is used for representing a corresponding relation between the obstacle data frame and the evaluation value;
a history evaluation value acquisition unit configured to acquire a history evaluation value corresponding to the history obstacle data frame;
an obstacle avoidance value determination unit configured to determine an obstacle avoidance value of the target obstacle according to the target evaluation value and the historical evaluation value;
a path planning unit configured to plan a path that bypasses a target obstacle indicated by the target obstacle data frame in response to determining that the obstacle avoidance value is greater than a preset threshold value.
7. The apparatus of claim 6, wherein the obstacle avoidance value determining unit is further configured to:
determining a historical decision value according to the historical evaluation value and a preset threshold value;
and determining an obstacle avoidance value of the target obstacle according to the target evaluation value, the historical decision value, a first preset weight corresponding to the target evaluation value, a second preset weight corresponding to the historical evaluation value and a third preset weight corresponding to the historical decision value.
8. The apparatus of claim 7, wherein the obstacle avoidance value determining unit is further configured to:
and in response to the fact that the target obstacle data frame is determined to be a first data frame, determining the historical evaluation value and the historical decision value to be a first preset value and a second preset value respectively, and determining an obstacle avoidance value of the target obstacle according to the first preset value, the second preset value, the target evaluation value, the first preset weight, the second preset weight and the third preset weight.
9. The apparatus of claim 8, wherein a sum of the first, second, and third preset weights is a third preset value.
10. The apparatus of claim 9, wherein the third preset weight is less than the first preset weight.
11. An electronic device for planning a path, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
12. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010602917.4A CN111724598B (en) | 2020-06-29 | 2020-06-29 | Method, device, equipment and storage medium for automatically driving and planning path |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010602917.4A CN111724598B (en) | 2020-06-29 | 2020-06-29 | Method, device, equipment and storage medium for automatically driving and planning path |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111724598A true CN111724598A (en) | 2020-09-29 |
| CN111724598B CN111724598B (en) | 2022-04-05 |
Family
ID=72569694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010602917.4A Active CN111724598B (en) | 2020-06-29 | 2020-06-29 | Method, device, equipment and storage medium for automatically driving and planning path |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111724598B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112327329A (en) * | 2020-11-25 | 2021-02-05 | 浙江欣奕华智能科技有限公司 | Obstacle avoidance method, target device, and storage medium |
| CN113050643A (en) * | 2021-03-19 | 2021-06-29 | 京东鲲鹏(江苏)科技有限公司 | Unmanned vehicle path planning method and device, electronic equipment and computer readable medium |
Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10129438A (en) * | 1996-11-06 | 1998-05-19 | Toyota Motor Corp | Automatic braking control device |
| JP2001283389A (en) * | 2000-03-29 | 2001-10-12 | Matsushita Electric Works Ltd | Obstacle detection device for vehicle |
| CN101395648A (en) * | 2006-03-01 | 2009-03-25 | 丰田自动车株式会社 | Vehicle path determining method and vehicle course determining device |
| KR20150121931A (en) * | 2014-04-22 | 2015-10-30 | 부산대학교 산학협력단 | UGV(Unmanned Ground Vehicle) Control System by using Hybrid Path Planning Method |
| CN105308620A (en) * | 2013-06-07 | 2016-02-03 | 索尼公司 | Information processing device, approaching object notification method, and program |
| US20180113234A1 (en) * | 2016-10-25 | 2018-04-26 | Cainiao Smart Logistics Holding Limited | System and method for obstacle detection |
| CN109143242A (en) * | 2018-09-07 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Barrier absolute velocity estimation method, system, computer equipment and storage medium |
| CN109427213A (en) * | 2017-09-05 | 2019-03-05 | 丰田自动车株式会社 | For the collision prevention device of vehicle, collision-proof method and the non-transitory storage medium for storing program |
| CN109583384A (en) * | 2018-11-30 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | Barrier-avoiding method and device for automatic driving car |
| CN109697875A (en) * | 2017-10-23 | 2019-04-30 | 华为技术有限公司 | Plan the method and device of driving trace |
| CN109739219A (en) * | 2018-12-05 | 2019-05-10 | 北京百度网讯科技有限公司 | Planing method, device, equipment and the readable storage medium storing program for executing of pass |
| CN109934164A (en) * | 2019-03-12 | 2019-06-25 | 杭州飞步科技有限公司 | Data processing method and device based on Trajectory Safety degree |
| CN109961631A (en) * | 2017-12-22 | 2019-07-02 | 深圳市城市交通规划设计研究中心有限公司 | The point recognition methods of road ponding and road ponding point identifying system |
| CN109960261A (en) * | 2019-03-22 | 2019-07-02 | 北京理工大学 | A kind of dynamic barrier preventing collision method based on collision detection |
| CN110320910A (en) * | 2019-07-01 | 2019-10-11 | 百度在线网络技术（北京）有限公司 | Evacuation control method, device, electronic equipment and the storage medium of vehicle |
| CN110379193A (en) * | 2019-07-08 | 2019-10-25 | 华为技术有限公司 | The conduct programming method and conduct programming device of automatic driving vehicle |
| CN110379203A (en) * | 2019-06-21 | 2019-10-25 | 江苏大学 | A kind of driving steering anti-collision warning method |
| CN110428092A (en) * | 2019-07-15 | 2019-11-08 | 南京邮电大学 | Multi-information fusion method and device, storage medium and terminal |
| CN110942668A (en) * | 2018-09-21 | 2020-03-31 | 丰田自动车株式会社 | Image processing system, image processing method, and image processing apparatus |
| CN110969287A (en) * | 2019-11-07 | 2020-04-07 | 郑州大学 | Shipboard aircraft guide path planning method |
| CN111238520A (en) * | 2020-02-06 | 2020-06-05 | 北京百度网讯科技有限公司 | Lane change path planning method and device, electronic equipment and computer readable medium |
| CN111260945A (en) * | 2020-01-18 | 2020-06-09 | 杭州后博科技有限公司 | Emergency vehicle avoiding method and system based on intelligent lamp pole |
| US20200180634A1 (en) * | 2018-12-11 | 2020-06-11 | Alpine Electronics, Inc. | Automated lane change system and methods |
| CN111338333A (en) * | 2018-12-18 | 2020-06-26 | 北京航迹科技有限公司 | System and method for autonomous driving |
-
2020
- 2020-06-29 CN CN202010602917.4A patent/CN111724598B/en active Active
Patent Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10129438A (en) * | 1996-11-06 | 1998-05-19 | Toyota Motor Corp | Automatic braking control device |
| JP2001283389A (en) * | 2000-03-29 | 2001-10-12 | Matsushita Electric Works Ltd | Obstacle detection device for vehicle |
| CN101395648A (en) * | 2006-03-01 | 2009-03-25 | 丰田自动车株式会社 | Vehicle path determining method and vehicle course determining device |
| CN105308620A (en) * | 2013-06-07 | 2016-02-03 | 索尼公司 | Information processing device, approaching object notification method, and program |
| KR20150121931A (en) * | 2014-04-22 | 2015-10-30 | 부산대학교 산학협력단 | UGV(Unmanned Ground Vehicle) Control System by using Hybrid Path Planning Method |
| US20180113234A1 (en) * | 2016-10-25 | 2018-04-26 | Cainiao Smart Logistics Holding Limited | System and method for obstacle detection |
| CN109427213A (en) * | 2017-09-05 | 2019-03-05 | 丰田自动车株式会社 | For the collision prevention device of vehicle, collision-proof method and the non-transitory storage medium for storing program |
| CN109697875A (en) * | 2017-10-23 | 2019-04-30 | 华为技术有限公司 | Plan the method and device of driving trace |
| CN109961631A (en) * | 2017-12-22 | 2019-07-02 | 深圳市城市交通规划设计研究中心有限公司 | The point recognition methods of road ponding and road ponding point identifying system |
| CN109143242A (en) * | 2018-09-07 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Barrier absolute velocity estimation method, system, computer equipment and storage medium |
| CN110942668A (en) * | 2018-09-21 | 2020-03-31 | 丰田自动车株式会社 | Image processing system, image processing method, and image processing apparatus |
| CN109583384A (en) * | 2018-11-30 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | Barrier-avoiding method and device for automatic driving car |
| CN109739219A (en) * | 2018-12-05 | 2019-05-10 | 北京百度网讯科技有限公司 | Planing method, device, equipment and the readable storage medium storing program for executing of pass |
| US20200180634A1 (en) * | 2018-12-11 | 2020-06-11 | Alpine Electronics, Inc. | Automated lane change system and methods |
| CN111338333A (en) * | 2018-12-18 | 2020-06-26 | 北京航迹科技有限公司 | System and method for autonomous driving |
| CN109934164A (en) * | 2019-03-12 | 2019-06-25 | 杭州飞步科技有限公司 | Data processing method and device based on Trajectory Safety degree |
| CN109960261A (en) * | 2019-03-22 | 2019-07-02 | 北京理工大学 | A kind of dynamic barrier preventing collision method based on collision detection |
| CN110379203A (en) * | 2019-06-21 | 2019-10-25 | 江苏大学 | A kind of driving steering anti-collision warning method |
| CN110320910A (en) * | 2019-07-01 | 2019-10-11 | 百度在线网络技术（北京）有限公司 | Evacuation control method, device, electronic equipment and the storage medium of vehicle |
| CN110379193A (en) * | 2019-07-08 | 2019-10-25 | 华为技术有限公司 | The conduct programming method and conduct programming device of automatic driving vehicle |
| CN110428092A (en) * | 2019-07-15 | 2019-11-08 | 南京邮电大学 | Multi-information fusion method and device, storage medium and terminal |
| CN110969287A (en) * | 2019-11-07 | 2020-04-07 | 郑州大学 | Shipboard aircraft guide path planning method |
| CN111260945A (en) * | 2020-01-18 | 2020-06-09 | 杭州后博科技有限公司 | Emergency vehicle avoiding method and system based on intelligent lamp pole |
| CN111238520A (en) * | 2020-02-06 | 2020-06-05 | 北京百度网讯科技有限公司 | Lane change path planning method and device, electronic equipment and computer readable medium |
Non-Patent Citations (1)
| Title |
|---|
| 单建华: "基于行为的实时路径规划", 《控制工程》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112327329A (en) * | 2020-11-25 | 2021-02-05 | 浙江欣奕华智能科技有限公司 | Obstacle avoidance method, target device, and storage medium |
| CN113050643A (en) * | 2021-03-19 | 2021-06-29 | 京东鲲鹏(江苏)科技有限公司 | Unmanned vehicle path planning method and device, electronic equipment and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111724598B (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112572462B (en) | Automatic driving control method and device, electronic equipment and storage medium | |
| CN112525551A (en) | Drive test method, device, equipment and storage medium for automatic driving vehicle | |
| CN111694287A (en) | Obstacle simulation method and device in unmanned simulation scene | |
| CN111724598B (en) | Method, device, equipment and storage medium for automatically driving and planning path | |
| CN111273268A (en) | Obstacle type identification method and device and electronic equipment | |
| CN111680362A (en) | Method, device and equipment for acquiring automatic driving simulation scene and storage medium | |
| CN111666891A (en) | Method and apparatus for estimating obstacle motion state | |
| CN111652153B (en) | Scene automatic identification method and device, unmanned vehicle and storage medium | |
| CN110703732A (en) | Correlation detection method, device, equipment and computer readable storage medium | |
| CN113071476A (en) | Autonomous parking method, device and equipment and automatic driving vehicle | |
| CN111361560B (en) | Method and device for controlling vehicle running in automatic driving and electronic equipment | |
| EP4145408A1 (en) | Obstacle detection method and apparatus, autonomous vehicle, device and storage medium | |
| CN110866504B (en) | Method, device and equipment for acquiring annotation data | |
| CN110796191B (en) | Trajectory classification method and device | |
| CN112793570A (en) | Control method, device, equipment and storage medium for automatic driving vehicle | |
| CN110764509A (en) | Task scheduling method, device, equipment and computer readable storage medium | |
| CN110798681B (en) | Monitoring method and device of imaging equipment and computer equipment | |
| CN111731240A (en) | Emergency brake rationality evaluation method, device, equipment and storage medium | |
| CN111563046B (en) | Method and device for generating information | |
| CN111596086B (en) | Method and device for estimating speed of obstacle in automatic driving and electronic equipment | |
| CN110728721B (en) | Method, device and equipment for acquiring external parameters | |
| CN111611902B (en) | Method, device, equipment and storage medium for detecting vehicle violation | |
| CN111959496A (en) | Model generation method and device for vehicle transverse control and electronic equipment | |
| CN110689090A (en) | Image storage method and device | |
| CN113008250A (en) | Unmanned vehicle navigation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |